[dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE instructions.

I probably shouldn't stick my nose into this, but I can't help myself. An experienced programmer will tend to ignore the documentation for a routine named "blahblah_memcmp" and just assume it functions like memcmp. Whether or not there's currently a use case in DPDK is completely irrelevant

[dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE instructions.

Hi Ravi, > > From: Ravi Kerur [mailto:rkerur at gmail.com] > Sent: Monday, May 11, 2015 6:43 PM > To: Ananyev, Konstantin > Cc: Matt Laswell; dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE > instructions. > > Hi Konstantin, > > > On Mon, May 11, 2015 at

[dpdk-dev] [PATCH v7 2/2] Update Docs for new EXTRA_LDLIBS variable

Signed-off-by: Keith Wiles --- doc/build-sdk-quick.txt | 1 + doc/guides/prog_guide/dev_kit_build_system.rst | 2 ++ doc/guides/prog_guide/dev_kit_root_make_help.rst | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/doc/build-sdk-quick.txt

[dpdk-dev] [PATCH v7 1/2] Simplify the ifdefs in rte.app.mk

Trying to simplify the ifdefs in rte.app.mk to make the code more readable and maintainable by moving LDLIBS variable to use the same style as LDLIBS-y being used in the rest of the code. Added a new variable called EXTRA_LDLIBS to be used by example apps instead of using

[dpdk-dev] [RFC PATCHv2 2/2] example app showing pktdevs used in a chain

This is a trivial example showing code which is using ethdevs and rings in a neutral manner, with the same piece of pipeline code passing mbufs along a chain without ever having to query its source or destination type. Signed-off-by: Bruce Richardson --- examples/pktdev/Makefile | 57

[dpdk-dev] [RFC PATCHv2 1/2] Add example pktdev implementation

This commit demonstrates what a minimal API for all packet handling might look like. It provides common APIs for RX and TX, by wrapping the types as appropriate. Implementations provided for ring, ethdev and kni. Signed-off-by: Bruce Richardson --- config/common_bsdapp | 5 ++

[dpdk-dev] [RFC PATCHv2 0/2] pktdev as wrapper type

Hi all, after a small amount of offline discussion with Marc Sune, here is an alternative proposal for a higher-level interface - aka pktdev - to allow a common Rx/Tx API across device types handling mbufs [for now, ethdev, ring and KNI]. The key code is in the first patch fo the set - the second

[dpdk-dev] [PATCH] lib: syntax cleanup

Remove extra parenthesis from return statements. Signed-off-by: Ferruh Yigit --- lib/librte_cmdline/cmdline_parse_etheraddr.c | 10 ++--- lib/librte_cmdline/cmdline_parse_ipaddr.c | 38 - lib/librte_cmdline/cmdline_parse_num.c | 24 +--

[dpdk-dev] [PATCHv2] app/ and examples/ fix default mbuf size

> > v2 changes: > > - add a new macro into rte_mbuf.h > > - make samples to use that new macro > > > > > > Fixes: dfb03bbe2b ("app/testpmd: use standard functions to initialize > > mbufs and mbuf pool"). > > Latest mbuf changes (priv_size addition and related fixes) > > exposed small problem with

[dpdk-dev] [PATCH] eal/bsdapp: fix compilation on FreeBSD

> Fixes: 6065355a "pci: make device id tables const" > > Following the above commit, compilation on FreeBSD with clang was broken, > giving the error message: > > .../lib/librte_eal/bsdapp/eal/eal_pci.c:438:16: fatal error: assigning to > 'struct rte_pci_id *' from 'const struct rte_pci_id

[dpdk-dev] [RFC PATCH 0/8] reduce header dependency on rte_mbuf.h

> > A large number of our header files and libraries are dependent on one > > another, > > which can lead to problems with circular dependencies if trying to tie some > > of > > those libraries together, e.g. when prototyping with pktdev, or other > > schemes > > to get a common API for

[dpdk-dev] DPDK Community Call - Beyond DPDK 2.0

This is just a reminder that this call is on tomorrow, at the following times, which is just under 24 hours from now. Dublin (Ireland) - Tuesday, May 12, 2015 at 4:00:00 PM IST UTC+1 hour San Francisco (U.S.A. - California) - Tuesday, May 12, 2015 at 8:00:00 AM PDT UTC-7 hours Phoenix (U.S.A. -

[dpdk-dev] [PATCH 4/6] rte_sched: allow reading without clearing

2015-04-29 10:04, Stephen Hemminger: > The rte_sched statistics API should allow reading statistics without > clearing. Make auto-clear optional. > > Signed-off-by: Stephen Hemminger > --- > app/test/test_sched.c| 4 ++-- > examples/qos_sched/stats.c | 16 +++- >

[dpdk-dev] [PATCH 2/6] rte_sched: expand scheduler hierarchy for more VLAN's

2015-04-29 10:04, Stephen Hemminger: > --- a/lib/librte_mbuf/rte_mbuf.h > +++ b/lib/librte_mbuf/rte_mbuf.h > @@ -285,7 +285,10 @@ struct rte_mbuf { > /**< First 4 flexible bytes or FD ID, dependent on >PKT_RX_FDIR_* flag in ol_flags. */ >

[dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE instructions.

Hi Konstantin, On Mon, May 11, 2015 at 12:35 PM, Ananyev, Konstantin < konstantin.ananyev at intel.com> wrote: > > Hi Ravi, > > > > > From: Ravi Kerur [mailto:rkerur at gmail.com] > > Sent: Monday, May 11, 2015 6:43 PM > > To: Ananyev, Konstantin > > Cc: Matt Laswell; dev at dpdk.org > >

[dpdk-dev] [PATCH 2/6] rte_sched: expand scheduler hierarchy for more VLAN's

On Mon, May 11, 2015 at 10:32:59AM -0700, Stephen Hemminger wrote: > On Mon, 11 May 2015 17:20:07 + > Neil Horman wrote: > > > Have you run this through the ABI checker? Seems like this would alter > > lots of > > pointer offsets. > > Neil > > No, I have not run it through ABI checker. >

[dpdk-dev] [PATCH v7 08/10] ixgbe: enable rx queue interrupts for both PF and VF

On 5/6/2015 2:36 AM, Stephen Hemminger wrote: > On Tue, 5 May 2015 13:39:44 +0800 > Cunming Liang wrote: > >> >> +/* set max interrupt vfio request */ >> +if (pci_dev->intr_handle.vec_en) { >> +pci_dev->intr_handle.max_intr = hw->mac.max_rx_queues + >> +

[dpdk-dev] [PATCH 2/6] rte_sched: expand scheduler hierarchy for more VLAN's

On Mon, May 11, 2015 at 10:07:47AM -0700, Stephen Hemminger wrote: > From: Stephen Hemminger > > The QoS subport is limited to 8 bits in original code. > But customers demanded ability to support full number of VLAN's (4096) > therefore use the full part of the tag field of mbuf. > > Resize the

[dpdk-dev] [PATCH v6 7/8] igb: enable rx queue interrupts for PF

On 3/21/2015 4:51 AM, Stephen Hemminger wrote: > On Fri, 27 Feb 2015 12:56:15 +0800 > Cunming Liang wrote: > >> >> /* >> + * It clears the interrupt causes and enables the interrupt. >> + * It will be called once only during nic initialized. >> + * >> + * @param dev >> + * Pointer to

[dpdk-dev] [PATCH v7 09/10] igb: enable rx queue interrupts for PF

On 5/6/2015 7:16 AM, Stephen Hemminger wrote: > On Tue, 5 May 2015 13:39:45 +0800 > Cunming Liang wrote: > >> The patch does below for igb PF: >> - Setup NIC to generate MSI-X interrupts >> - Set the IVAR register to map interrupt causes to vectors >> - Implement interrupt enable/disable

[dpdk-dev] TX performance regression caused by the mbuf cachline split

Hi Luke, thanks for your suggestion, I actually looked at how your packet generator in SnabbSwitch works before and it's quite clever. But unfortunately that's not what I'm looking for. I'm looking for a generic solution that works with whatever NIC is supported by DPDK and I don't want to

[dpdk-dev] Issues met while running openvswitch/dpdk/virtio inside the VM

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Pravin Shelar > Sent: Friday, May 8, 2015 2:20 AM > To: Oleg Strikov > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] Issues met while running openvswitch/dpdk/virtio > inside the VM > > On Thu, May 7, 2015 at

[dpdk-dev] [RFC PATCH 0/2] Move PMDs out of lib directory

2015-05-07 16:35, Bruce Richardson: > The "lib" directory is getting very crowded, with both general libs and > poll mode drivers in it. This patch set proposes to move the PMDs out of the > lib folder and to put them in a separate "pmds" folder. This should help > with code browse-ability as the

[dpdk-dev] [PATCH 6/6] doc: extend commands in testpmd

Modify the doc about flow director commands to support l2_payload flow type and filtering in VFs. Signed-off-by: Jingjing Wu --- doc/guides/testpmd_app_ug/testpmd_funcs.rst | 15 --- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git

[dpdk-dev] [PATCH 5/6] testpmd: extend commands

This patch extends commands to support l2_payload flow type and filtering in VFs of flow director. Signed-off-by: Jingjing Wu --- app/test-pmd/cmdline.c | 87 ++ 1 file changed, 81 insertions(+), 6 deletions(-) diff --git a/app/test-pmd/cmdline.c

[dpdk-dev] [PATCH 4/6] i40e: extend flow diretcor to support filtering in VFs

This patch extends flow diretcor to filterting in VFs. Signed-off-by: Jingjing Wu --- lib/librte_pmd_i40e/i40e_fdir.c | 15 --- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/lib/librte_pmd_i40e/i40e_fdir.c b/lib/librte_pmd_i40e/i40e_fdir.c index 27c2102..2f4c247

[dpdk-dev] [PATCH 3/6] ethdev: extend struct to support flow director in VFs

This patch extends struct rte_eth_fdir_flow_ext to support flow director in VFs. Signed-off-by: Jingjing Wu --- lib/librte_ether/rte_eth_ctrl.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/librte_ether/rte_eth_ctrl.h b/lib/librte_ether/rte_eth_ctrl.h index 0e30dd9..601a4d3 100644

[dpdk-dev] [PATCH 2/6] i40e: extend flow diretcor to support l2_payload flow type

This patch extends flow diretcor to support l2_payload flow type in i40e driver. Signed-off-by: Jingjing Wu --- lib/librte_pmd_i40e/i40e_fdir.c | 24 +--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/lib/librte_pmd_i40e/i40e_fdir.c

[dpdk-dev] [PATCH 1/6] ethdev: add struct rte_eth_l2_flow to support l2_payload flow type

This patch adds a new struct rte_eth_l2_flow to support l2_payload flow type Signed-off-by: Jingjing Wu --- lib/librte_ether/rte_eth_ctrl.h | 8 1 file changed, 8 insertions(+) diff --git a/lib/librte_ether/rte_eth_ctrl.h b/lib/librte_ether/rte_eth_ctrl.h index 498fc85..0e30dd9 100644

[dpdk-dev] [PATCH 0/6] extend flow director to support L2_paylod type and VF filtering in i40e driver

This patch set extends flow director to support L2_paylod type and VF filtering in i40e driver. Jingjing Wu (6): ethdev: add struct rte_eth_l2_flow to support l2_payload flow type i40e: extend flow diretcor to support l2_payload flow type ethdev: extend struct to support flow director in

[dpdk-dev] [PATCH 1/4] pci: allow access to PCI config space

On Mon, May 11, 2015 at 08:23:59AM -0700, Stephen Hemminger wrote: > Ok will stub out the pci_config stuff for BSD. > But I don't have time or resources to do real BSD support. > > Also, the whole bnx2x driver loads firmware and that probably has dependencies > that are different on BSD > Thats

[dpdk-dev] [PATCH v7 02/10] eal/linux: add rte_epoll_wait/ctl support

On 5/8/2015 10:57 AM, Stephen Hemminger wrote: > On Tue, 5 May 2015 13:39:38 +0800 > Cunming Liang wrote: > >> +else if (rc < 0) { >> +/* epoll_wait fail */ >> +RTE_LOG(ERR, EAL, "epoll_wait returns with fail %s\n", >> +strerror(errno)); > In

[dpdk-dev] [PATCH v6 0/6] enicpmd: Cisco Systems Inc. VIC Ethernet PMD

Hi Sujith, 2015-02-27 08:09, Sujith Sankar: > Hi Thomas, > > No update on it from my side :-( > It would take some more time for me to start working on it (and flow > director api) as a few other things are keeping me busy. [...] Documentation was split to better welcome new NICs:

[dpdk-dev] [PATCH] enic: add support for enic in nic_uio driver for FreeBSD

2015-05-07 12:57, David Marchand: > On Thu, May 7, 2015 at 11:23 AM, Bruce Richardson wrote: > > On Thu, May 07, 2015 at 09:19:09AM +0530, Sujith Sankar wrote: > > > This patch adds support for enic in the nic_uio driver so that enic > > could be used on FreeBSD. > > > > > > Signed-off-by: Sujith

[dpdk-dev] TX performance regression caused by the mbuf cachline split

Hi Paul, On 11 May 2015 at 02:14, Paul Emmerich wrote: > Another possible solution would be a more dynamic approach to mbufs: Let me suggest a slightly more extreme idea for your consideration. This method can easily do > 100 Mpps with one very lightly loaded core. I don't know if it works

[dpdk-dev] Getting started - sanity check

On Sat, May 09, 2015 at 04:27:12PM +, Clark, Gilbert wrote: > > Hi folks: > > I'm brand new to DPDK.? Read about it off and on occasionally, but never had > the chance to sit down and play with things until now. ?It's been fun so far: > just been working on a few toy applications to get

[dpdk-dev] [PATCH] kni: fix compilation issue on kernel 4.0.0

> Due to API changes in function pointer ndo_bridge_setlink > (commit ad41faa8) and the rename of functions vlan_tx_* > (commit df8a39de) in kernel 4.0, DPDK would not build. > > This patch adds the properly checks to fix the compilation. > > Reported-by: Stephen Hemminger > Signed-off-by:

[dpdk-dev] [PATCH v3] kni: fix compilation issue in KNI vhost on kernel 3.19/4.0

> Due to commit c0371da6 in kernel 3.19, which removed msg_iov > and msg_iovlen from struct msghdr, DPDK would not build. > Also, functions memcpy_toiovecend and memcpy_fromiovecend > were removed in commits ba7438ae and 57dd8a07, being substituted by > copy_from_iter and copy_to_iter. > > This

[dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE instructions.

Hi Konstantin, On Mon, May 11, 2015 at 2:51 AM, Ananyev, Konstantin < konstantin.ananyev at intel.com> wrote: > Hi Ravi, > > > -Original Message- > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ravi Kerur > > Sent: Friday, May 08, 2015 11:55 PM > > To: Matt Laswell > > Cc:

[dpdk-dev] [PATCH 2/6] rte_sched: expand scheduler hierarchy for more VLAN's

On Mon, 11 May 2015 17:20:07 + Neil Horman wrote: > Have you run this through the ABI checker? Seems like this would alter lots > of > pointer offsets. > Neil No, I have not run it through ABI checker. It would change the ABI for applications using qos_sched but will not change layout of

[dpdk-dev] [PATCH 1/4] pci: allow access to PCI config space

On Mon, 11 May 2015 12:54:54 + Neil Horman wrote: > On Thu, May 07, 2015 at 04:25:32PM -0700, Stephen Hemminger wrote: > > From: Stephen Hemminger > > > > Some drivers need ability to access PCI config (for example for power > > management). This adds an abstraction to do this; only

[dpdk-dev] [PATCH 1/4] pci: allow access to PCI config space

On Mon, 11 May 2015 11:37:08 -0400 Neil Horman wrote: > On Mon, May 11, 2015 at 08:23:59AM -0700, Stephen Hemminger wrote: > > Ok will stub out the pci_config stuff for BSD. > > But I don't have time or resources to do real BSD support. > > > > Also, the whole bnx2x driver loads firmware and

[dpdk-dev] [PATCH v3] kni: fix compilation issue in KNI vhost on kernel 3.19/4.0

2015-05-10 23:01, De Lara Guarch, Pablo: > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > I have the following errors with Linux 4.0.1: > > > > lib/librte_eal/linuxapp/kni/igb_main.c:2321:2: error: initialization from > > incompatible pointer type > > .ndo_bridge_setlink =

[dpdk-dev] [PATCH 6/6] rte_sched: use correct log level

The setup messages should be at DEBUG level since they are not important for normal operation of system. The messages about problems should be at NOTICE or ERR level. Signed-off-by: Stephen Hemminger --- lib/librte_sched/rte_sched.c | 15 +-- 1 file changed, 9 insertions(+), 6

[dpdk-dev] [PATCH 5/6] rte_sched: don't put tabs in log messages

From: Stephen Hemminger syslog does not like tabs in log messages; tab gets translated to #011 Signed-off-by: Stephen Hemminger --- lib/librte_sched/rte_sched.c | 14 +++--- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git

[dpdk-dev] [PATCH 4/6] rte_sched: allow reading without clearing

The rte_sched statistics API should allow reading statistics without clearing. Make auto-clear optional. Signed-off-by: Stephen Hemminger --- app/test/test_sched.c| 4 ++-- examples/qos_sched/stats.c | 22 +++--- lib/librte_sched/rte_sched.c | 44

[dpdk-dev] [PATCH 3/6] rte_sched: keep track of RED drops

From: Stephen Hemminger Add new statistic to keep track of drops due to RED. Signed-off-by: Stephen Hemminger --- lib/librte_sched/rte_sched.c | 31 ++- lib/librte_sched/rte_sched.h | 6 ++ 2 files changed, 32 insertions(+), 5

[dpdk-dev] [PATCH 2/6] rte_sched: expand scheduler hierarchy for more VLAN's

From: Stephen Hemminger The QoS subport is limited to 8 bits in original code. But customers demanded ability to support full number of VLAN's (4096) therefore use the full part of the tag field of mbuf. Resize the pipe as well to allow for more pipes in future and avoid

[dpdk-dev] [PATCH 1/6] rte_sched: make RED optional at runtime

From: Stephen Hemminger Want to be able to build with RTE_SCHED_RED enabled but allow disabling RED on a per-queue basis at runtime. RED is disabled unless min/max thresholds set. Signed-off-by: Stephen Hemmminger --- lib/librte_sched/rte_sched.c | 9 + 1 file

[dpdk-dev] [PATCH v3 0/6] rte_sched: cleanups and API changes

This is 3rd rev of DPDK changes to QoS scheduler. The change from last revision was to fix the example and fix whitespace. Stephen Hemminger (6): rte_sched: make RED optional at runtime rte_sched: expand scheduler hierarchy for more VLAN's rte_sched: keep track of RED drops rte_sched:

[dpdk-dev] [PATCH] librte_eal:Using compiler memory barrier for IA processor's rte_wmb/rte_rmb.

Hi Dong, > -Original Message- > From: Wang Dong [mailto:dong.wang.pro at hotmail.com] > Sent: Saturday, May 09, 2015 11:24 AM > To: Ananyev, Konstantin; dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH] librte_eal:Using compiler memory barrier for > IA processor's rte_wmb/rte_rmb. > >

[dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE instructions.

Hi Ravi, > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ravi Kerur > Sent: Friday, May 08, 2015 11:55 PM > To: Matt Laswell > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE > instructions. > > On Fri, May 8, 2015

[dpdk-dev] [PATCH 1/4] pci: allow access to PCI config space

On Thu, May 07, 2015 at 04:25:32PM -0700, Stephen Hemminger wrote: > From: Stephen Hemminger > > Some drivers need ability to access PCI config (for example for power > management). This adds an abstraction to do this; only implemented > on Linux, but should be possible on BSD. > >

[dpdk-dev] [PATCH 1/4] pci: allow access to PCI config space

Ok will stub out the pci_config stuff for BSD. But I don't have time or resources to do real BSD support. Also, the whole bnx2x driver loads firmware and that probably has dependencies that are different on BSD

[dpdk-dev] [PATCH v7 08/10] ixgbe: enable rx queue interrupts for both PF and VF

On Mon, 11 May 2015 13:31:04 +0800 "Liang, Cunming" wrote: > > Since MSI-X vectors are limited on many hardware platforms, this whole API > > should be changed so that max_intr is based on number of rx_queues actually > > used by the application. That means the setup needs to move from init to

[dpdk-dev] Intel fortville not working with multi-segment

Hi, I am using PF pass-through and it doesn't work even with 2000 bytes of server response page size. Looks like the first segment of each session is not received. When i am changing the server response size to 1000 bytes, all works as expected. I am working with dpdk 1.8 version. Any idea

[dpdk-dev] TX performance regression caused by the mbuf cachline split

Hi, this is a follow-up to my post from 3 weeks ago [1]. I'm starting a new thread here since I now got a completely new test setup for improved reproducibility. Background for anyone that didn't catch my last post: I'm investigating a performance regression in my packet generator [2] that

[dpdk-dev] Intel fortville not working with multi-segment

Hi Nissim Are you using PF pass-through or VF pass-through? For PF pass-through, you might have already gotten the fix. For VF pass-through, there is a bug fix which is needed for supporting jumbo frame and multiple mbuf. http://www.dpdk.org/dev/patchwork/patch/4641/ Regards, Helin >

[dpdk-dev] [PATCH v3] kni: fix compilation issue in KNI vhost on kernel 3.19/4.0

Hi Pablo, 2015-05-05 15:08, Pablo de Lara: > Due to commit c0371da6 in kernel 3.19, which removed msg_iov > and msg_iovlen from struct msghdr, DPDK would not build. > Also, functions memcpy_toiovecend and memcpy_fromiovecend > were removed in commits ba7438ae and 57dd8a07, being substituted by >

[dpdk-dev] [PATCH v3] kni: fix compilation issue in KNI vhost on kernel 3.19/4.0

Hi Thomas, > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Sunday, May 10, 2015 10:26 PM > To: De Lara Guarch, Pablo > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3] kni: fix compilation issue in KNI vhost on > kernel 3.19/4.0 > > Hi